Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3135 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3442. Min Range: -6.3442
Max Act: 6.3442. Min Act: -0.1700
Data Index: 4056744 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3442. Min Range: -6.3442
Max Act: 6.0629. Min Act: -0.1700
Data Index: 8631551 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.9067. Min Act: -0.1700
Data Index: 8635337 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.9067. Min Act: -0.1700
Data Index: 6902193 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.8442. Min Act: -0.1700
Data Index: 6831956 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.8129. Min Act: -0.1700
Data Index: 8068099 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.7192. Min Act: -0.1700
Data Index: 3771683 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.6254. Min Act: -0.1700
Data Index: 3175915 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.6567. Min Act: -0.1700
Data Index: 1063697 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.6254. Min Act: -0.1700
Data Index: 4538519 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.6254. Min Act: -0.1700
Data Index: 4299045 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.6254. Min Act: -0.1700
Data Index: 8374553 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.6254. Min Act: -0.1700
Data Index: 7283547 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.5317. Min Act: -0.1700
Data Index: 1677555 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.5004. Min Act: -0.1700
Data Index: 5259133 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.5004. Min Act: -0.1700
Data Index: 6853392 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.5004. Min Act: -0.1700
Data Index: 6154846 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.4379. Min Act: -0.1700
Data Index: 134911 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.4379. Min Act: -0.1700
Data Index: 6717284 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.5004. Min Act: -0.1700
Data Index: 7444749 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19